On the equivalence of confidence interval estimation based on frequentist model averaging and least-squares of the full model in linear regression
|
|
- Patrick Moore
- 5 years ago
- Views:
Transcription
1 Working Paper 2016:1 Department of Statistics On the equivalence of confidence interval estimation based on frequentist model averaging and least-squares of the full model in linear regression Sebastian Ankargren and Shaobo Jin
2
3 Working Paper 2016:1 April 2016 Department of Statistics Uppsala University Box 513 SE UPPSALA SWEDEN Working papers can be downloaded from Title: On the equivalence of confidence interval estimation based on frequentist model averaging and least-squares for the full model in linear regression Author: Sebastian Ankargren & Shaobo Jin
4 On the equivalence of confidence interval estimation based on frequentist model averaging and least squares of the full model in linear regression Sebastian Ankargren and Shaobo Jin Department of Statistics, Uppsala University April 5, 2016 Abstract In many applications of linear regression models, model selection is vital. However, randomness due to model selection is commonly ignored in post-model selection inference. In order to account for the model selection uncertainty in these linear models, least squares frequentist model averaging has been proposed recently. In this paper, we show that the confidence interval from model averaging is asymptotically equivalent to the confidence interval from the full model. Furthermore, we demonstrate that this equivalence also holds in finite samples if the parameter of interest is a linear function of the regression coefficients. Keywords: Asymptotic equivalence Linear model Local asymptotics odel selection uncertainty Post-selection inference athematics Subject Classification 2000: 62E20 62J05 62J99 62F12 1 Introduction In many situations in applied statistics, there is no model structure known to the researcher, but a set of plausible alternatives. Commonly, to pick one model from this set of candidates, information criteria such as AIC Akaike, 1974 and BIC Schwarz, 1978 are used. This can have detrimental effects on subsequent inference since the model selection step itself is stochastic and thus subject to uncertainty, an uncertainty which inference post-model selection usually fails to account for. This issue is studied sebastian.ankargren@statistics.uu.se shaobo.jin@statistics.uu.se 1
5 in detail by e.g. Pötscher 1991; Kabaila 1995; Kabaila and Leeb 2006; Leeb and Pötscher 2005; also see Berk et al 2013 for a promising way of doing inference post-model selection. It is often by this inability of model selection to incorporate the randomness attached to it in post-selection inference that frequentist model averaging is motivated, advocating that it may serve as a better, more truthful alternative. For example, it is claimed that model averaging compromises across a set of competing models, and in doing so, incorporates model uncertainty into the conclusions about the unknown parameters Wan et al, 2010, p Hjort and Claeskens 2003 developed a frequentist model averaging machinery under the likelihood framework. They proposed a confidence interval that captures the randomness in model selection. However, Wang and Zhou 2013 showed that the proposed interval is asymptotically equivalent to the confidence interval obtained from the full model and that the finite sample confidence intervals are also equivalent if the parameter of interest is a linear combination of regression coefficients of a varying-coefficient partially linear model, which is regarded as the semi-parametric framework by the authors. The focus of this paper is the linear model using least squares. Least squares-based model averaging has previously been studied by for example Hansen 2007, Wan et al 2010, Hansen and Racine 2012, Liu and Okui 2013, Ando and Li 2014 and Cheng et al 2015, with a focus on prediction. Liu 2015 developed asymptotic distribution theory for frequentist model averaging estimators under the least squares framework, including results for allows and Jackknife model averaging Hansen, 2007; Hansen and Racine, 2012, and proposed a confidence interval in the spirit of Hjort and Claeskens In this article, we show that the inference we can make about the unknown parameters, using the distributional theory of Liu 2015, is in fact equivalent to what we can make just using the model including all possible covariates, either asymptotically or both in finite samples and asymptotically depending on the nature of the parameter of interest. From this perspective, there is no additional gain in turning to model averaging. Thus, this paper extends the work by Kabaila and Leeb 2006 and Wang and Zhou 2013 in that their criticism geared towards interval estimation based on Hjort and Claeskens 2003 is also valid for interval estimation in linear models based on Liu The remainder of the paper is organized as follows. Section 2 briefly reviews the key results in Liu 2015, Section 3 discusses the equivalence of the confidence interval and Section 4 concludes. Proofs are placed in Appendix A. 2 Frequentist model averaging In this section we briefly review the necessary aspects of Liu Assume the linear regression model y = Xβ Zγ e 1 in which y = y 1,...,y n is the n 1 response vector, X = x 1,...,x n the n p matrix of core regressors, Z = z 1,...,z n the n q matrix of auxiliary regressors, e = e 1,...,e n the n 1 vector of errors and β and γ are the p 1 and q 1 parameter 2
6 vectors. By the formulation of the model, the core regressors in X are necessarily included in all models, but those in Z are potential and subject to scrutiny. This does not restrict applications, however, as X may be an empty matrix or simply a vector of ones such that the intercept is always included. The error term is assumed to have a zero conditional mean, Ee i x i,z i = 0, but allowed to be both heteroskedastic and autocorrelated. Collect the regressors and the parameters in H = X,Z and θ = β,γ, respectively. The regression model 1 may then be written as y = Hθ e Suppose now that there is a set of candidate models. If this set consists of all nested models, then = q 1, and if it consists of all submodels, then = 2 q. Whatever the choice of model set, each model m is assumed to contain a unique combination of 0 q m q regressors from Z such that the mth model s subset of auxiliary regressors can be written as Z m = ZΠ m, where Z m is n q m and Π m is a q q m selection matrix. Since all models also include the full set of core regressors X, model m includes in total p q m regressors. For ease of notation and with no loss of generality, let the full model be ordered last in the set of models such that model is the full model including all regressors. The least squares estimator of θ in this model is ˆθ = H H 1 H y, whereas for submodel m, the estimator of θ m = β,γ m = β,γ Π m, a pq m 1 vector, is ˆθ m = H mh m 1 H my, 2 where H m = X,Z m = X,ZΠ m. For later use we also define θ m = β,γ mπ m, a p q 1 vector in which there are zeros placed in the positions corresponding to excluded variables in model m. Similarly, ˆθ m = ˆβ m, ˆγ m = ˆβ m, ˆγ mπ m where ˆθ m is p q 1 and ˆγ m is the q m last elements of ˆθ m in 2. For the asymptotic analysis local asymptotics are employed. This framework entails the following assumption. Assumption 1. γ = γ n = δ/ n, where δ is an unknown local parameter vector. Since the omitted variable bias in all models but the full is of order O1/ n under Assumption 1, n ˆθ m θ m does not diverge. Instead, we have the following: n ˆθ θ n ˆθ m θ m d N0,Q 1 ΩQ 1 d NA m δ,q 1 m Ω m Q 1 m 3 3
7 where A m = Q 1 m S mqs 0 I q Π m Π m and 0p q Ip 0 S 0 =, S I m = p qm q 0 q p Π m Q Q Q = xz Exi x = i Ex iz i Q zx Q zz Ez i x i Ez iz i n n Ω Ω Ω = xz 1 Exi x = lim n n j e ie j Ex i z j e ie j Ez i x j e ie j Ez i z j e ie j Ω zx Ω zz i=1 j=1 Q m = S mqs m, Ω m = S mωs m. The limiting distributions in 3 are results of the following assumption. Assumption 2. As n, n 1 H H p Q and n 1/2 H e d R N0,Ω. Suppose the ultimate goal is to make inference regarding the true value of a known, smooth function µ : R pq R evaluated at the unknown parameters; that is, we are interested in the true value of µθ. This is called the focus parameter. The model averaging estimator is a weighted average of the estimator for the focus parameter µθ in the individual submodels. The averaging estimator is µ = wm ˆδ ˆµ m, where wm ˆδ denotes the data-dependent weight for model m and ˆµ m should be understood as ˆµ m := µ ˆθ m = µ ˆβ m, ˆγ m, i.e. the function µ at the estimated values of β and γ m, with the q q m elements in γ not included in γ m set to 0. The local parameter, δ, can be unbiasedly, but not consistently, estimated asymptotically in the sense that ˆδ = n ˆγ d R δ = δ S 0Q 1 R Nδ,S 0Q 1 ΩQ 1 S 0. Let D θ be the derivative of µ with respect to the full parameter vector θ evaluated at the null points β,0. The key theorem in Liu 2015 underlying the results for a frequentist model averaging confidence interval for µ is stated next. d Theorem 1 Liu, If wm ˆδ wm R δ as n and Assumptions 1-2 hold, then n µ µ d D θ Q 1 R D θ wm R δ C m R δ where C m = P m Q I pq S 0 and P m = S m S mqs m 1 S m. 4
8 Proof. See Liu The proposed confidence interval rests on the idea of replacing limit quantities by finite sample counterparts. Thus, for sufficiently large n, it should be that n µ µ ˆD θ wm ˆδĈ m ˆδ app. N0,1 ˆκ where ˆκ is a consistent estimator of κ = D θ Q 1 ΩQ 1 D θ. Therefore, a confidence interval with asymptotic coverage of 1001 α% is µ b ˆδ z 1 α/2 ˆκ, µ b ˆδ z 1 α/2 ˆκ, 4 where b ˆδ = ˆD θ w m ˆδ Ĉ m ˆγ and z 1 α/2 is the 1 α/2 quantile of the standard normal distribution. 3 Equivalence of confidence intervals In this section we establish the equivalence of frequentist model averaging and full model confidence intervals. 3.1 Asymptotic equivalence Consider the case where there is a fixed model and that this model is the full model. By 3 and the delta theorem, the asymptotic distribution of the estimator of the focus parameter is n µ ˆθ µ θ d N 0,D θ Q 1 ΩQ 1 D θ. The confidence interval for µ in the full model based upon a finite-sample approximation to this asymptotic distribution is µ ˆθ z1 α/2 ˆκ, µ ˆθ z1 α/2 ˆκ, 5 where z is the 1 α/2 quantile of a standard normal distribution. Note that the interval in 5 has the same length as the interval in 4. It therefore follows that if the centers of the two intervals are asymptotically the same, then they are asymptotically equivalent. That is, equivalence holds if µ = ˆµ b ˆδ o p n 1/2. The existence of this particular relation is our main result, and it is established in the following theorem. The proof is placed in Appendix A. Theorem 2. The frequentist model averaging and full model confidence intervals in 4 and 5, respectively, are asymptotically equivalent. 5
9 Theorem 2 suggests that for large sample sizes, there are no gains in terms of interval estimation in using model averaging. A confidence interval based on least squares estimation of the full model instead offers the more compelling alternative, given its simplicity. 3.2 Small sample equivalence Theorem 2 shows that the confidence interval 5 is asymptotically equivalent to 4 for a general smooth and real-valued function µ θ. However, nothing is said about the finite sample properties, in which there may be substantial differences. In this section, we establish also small sample equivalence when µ θ = c θ, where c is a vector of known scalars. That is, the focus parameter is some fixed linear function of the regression coefficients. If the focus parameter is µ θ = c θ, the center of the full model confidence interval 5 is c ˆθ and the center of the model averaging confidence interval 4 is w m ˆδ ] Ĉ m ˆγ c [ w m ˆδ ˆθ m = c [ 1 ˆθ w m ˆδ ˆθ m ˆθ Ĉ m ˆγ ], since ˆD θ = c. The equality holds because Ĉ = 0 and ˆθ = ˆθ. Based on the center 6, we can establish the following theorem. Theorem 3. If µ θ = c θ, the confidence interval 5 is equivalent to the confidence interval 4 in finite samples, where c is a p q 1 constant vector. Theorem 3 says that the full model produces the same confidence interval as model averaging under some restricted cases. However, Theorem 3 says nothing about the small sample equivalence for other cases, e.g., β 1 /β 2 or expβ 1. We conjecture that the small sample equivalence is likely to fail for focus parameters not of the form µ θ = c θ. This is illustrated in the following example. Example 1. Consider a model with two regressors y = Xβ Zγ ɛ, where γ = δ/ n. From the above discussion, the confidence interval of β from the full model is the same as that from model averaging, both asymptotically and in a finite sample. In particular, from Theorem 2 we know that, for any differentiable function h, the confidence interval of hβ from the full model is asymptotically the same as that from model averaging. However, the above discussion says nothing about the finite sample equivalence. In this example, consider hβ = β 2. The center from the model averaging confidence interval is w 1 ˆδ ˆβ 2 1 [ 1 w 1 ˆδ ] ˆβ 2 2w 1 ˆδ ˆβ ˆQ 1 ˆQ xz ˆγ. 6 6
10 Observe that ˆβ 1 = ˆQ 1 X y/n, ˆβ = ˆQ zz X y/n ˆQ xz Z y/n ˆQ ˆQ zz ˆQ 2 xz and ˆγ = ˆQ xz X y/n ˆQ Z y/n. ˆQ ˆQ zz ˆQ 2 xz Then, the difference in two centers is w 1 ˆδ [ ˆβ 2 1 ˆβ 2 2 ˆβ ˆQ 1 ˆQ xz ˆγ ], which is zero if and only if w 1 ˆδ = 0 or ˆβ 1 2 ˆβ 2 2 ˆβ ˆQ 1 ˆQ xz ˆγ = 0. The former means the full model receives the total weight. Plugging in the expressions of ˆβ 1, ˆβ, and ˆγ, the latter satisfies ˆβ 1 2 ˆβ 2 2 ˆβ ˆQ 1 ˆQ xz ˆγ = 1 n 2 ˆQ 2 xz ˆQ xz X y ˆQ Z y 2 ˆQ 2 ˆQ ˆQ zz ˆQ xz 2 2, which is zero only if ˆQ xz X y = ˆQ Z y or ˆQ xz = 0. If X and Z are correlated, the two intervals are likely to be different. 4 Conclusion In this work, we have studied the frequentist model averaging confidence interval for linear models proposed by Liu Using similar techniques as Wang and Zhou 2013, our key result is that the model averaging confidence interval is asymptotically equivalent to the interval obtained by use of least squares estimation in the full model. Furthermore, we also provide the stronger result that the intervals are exactly equivalent in finite samples if µ, the function defining the focus parameter, is linear. While the results are disadvantageous to model averaging, they should be interpreted with care. Numerous studies have illustrated impressive performance of model averaging in terms of prediction. This strand of the literature is separate from what we consider and thus remains unaffected by the conclusion herein. In fact, the good predictive performance may instead suggest that with other methods, we may be able to increase the efficiency of our confidence intervals by resorting to model averaging. This, however, we leave for further research. A Proofs Proof of Theorem 2. A proof technique similar to that used by Wang and Zhou 2013 is also employed here, but applied to the different problem setting that we have. As already noted in the text, the intervals have the same length and thus what needs to be proved is that the centers are asymptotically equal. To this end, let R N 0,Ω. Lemma 1 in Liu 2015 indicates that n ˆθ m θ m = Q 1 m S mqs 0 Iq Π mπ m δ Q 1 m S mr o p 1, 7 where θ m = β,δ m/ n. For simplicity and without loss of generality, assume that the set of models is ordered in such a way that denotes the full model. If m =, 7
11 then Π = I, S = I, and Q 1 = Q 1, so then what remains is n ˆθ θ = Q 1 R o p 1, where θ = β,δ / n. Thus, R = nq ˆθ θ o p 1 and 7 becomes n ˆθ m θ m = Q 1 m S mqs 0 Iq Π mπ m δ Q 1 m S mq n ˆθ θ o p 1.8 By rules for inverses of block matrices e.g., Theorem in Harville, 1997, Q 1 Q 1 Q xz Π mk m Π m Q zx Q 1 Q 1 Q xz Π mk m where Q 1 m = K m Π m Q zx Q 1 K m, 9 K m = [ Π m Qzz Q zx Q 1 Q xz Π m ] 1 = Πm K 1 Π m with K = Q zz Q zx Q 1 1. Q xz Plugging 9 into Q 1 m S mq yields Q 1 m S mq Ip A = m, 0 B m where A m = Q 1 Q xz Iq Π mk m Π m K 1 and B m = K m Π m K 1. Thus, 8 can be expressed as n ˆθ m θ m = Am B m Iq Π Ip A mπ m δ m 0 B m ˆθ θ o p 1. Recall that ˆθ m = ˆβ m, ˆδ m/ n and θm = β,δ m/ n, where δ m = Π m δ. Then n ˆβ m β = A m δ n ˆβ β A m n ˆγ δ o p 1, 11 n n ˆγ m δ m = B m Iq Π n mπ m δ Bm n ˆγ δ o p 1, 12 n where we have used that I q Π mb m I q Π mπ m = I q Π mb m. The Taylor expansion of n µ ˆβ m,π m ˆγ m µ β,δ/ n around β,δ/ n is [ n µ ] ˆβ m,π δ m ˆγ m µ β, n = µ n ˆβ m β µ n Π m ˆγ m δ o p 1, 13 β where the partial derivatives are evaluated at β,0 q 1 because of the continuous mapping theorem. Likewise, for the full model, [ n µ ] δ ˆβ, ˆγ µ β, n = µ n ˆβ β µ n ˆγ δ o p β 8
12 We then get n µ = w m ˆδ nµ ˆβ m,π m ˆγ m Rewriting = w m ˆδ [ δ nµ β, n µ n ˆβ m β β µ n Π m ˆγ m δ ] o p 1 by 13 = δ µ nµ β, n ˆβ β n β w m ˆδ µ [ A m δ n ˆγ δ ] β w m ˆδ [ µ n Π m ˆγ m δ ] o p 1 by 11. Π m ˆγ m δ = Π m ˆγ m δ m n I q Π mπ m δ n and using 12 δ µ n µ = nµ β, n ˆβ β n β w m ˆδ µ [ A m δ n ˆγ δ ] β w m ˆδ [ µ Π mb m { Iq Π mπ m δ n ˆγ δ } I q Π mπ m δ ] o p 1 9
13 Applying 14 yields µ n µ = nµ ˆβ, ˆγ n ˆγ δ w m ˆδ µ [ A m δ n ˆγ δ ] β w m ˆδ [ µ w m ˆδ µ Π mb m { Iq Π mπ m δ n ˆγ δ } I q Π mπ m δ ] o p 1 = nµ ˆβ, ˆγ w m ˆδ [ µ µ A m Π mb ] m I q n ˆγ δ β w m ˆδ [ µ µ A m Π β mb m Iq Π ] mπ m δ Iq Π mπ m δ op 1 A m ˆγ δ = nµ ˆβ, ˆγ w m ˆδ D θ Π mb m I q w m ˆδ D θ A m Π mb m I q Π δ mπ m w m ˆδ µ Iq Π mπ m δ op Further, using C m = S m Q 1 m S mq I S 0 = A m Π mb m I q 16 in 15 yields n µ = nµ ˆβ, ˆγ [ D θ w m ˆδ [ w m ˆδ µ D θ w m ˆδ C m ] ˆγ δ n A m ] δ Π mb m I q Π mπ m Iq Π mπ m δ op The center of the confidence interval proposed in Liu 2015 is µ b ˆδ, where b ˆδ = ˆD θ w m ˆδ Ĉ m ˆγ with ˆδ = n ˆγ. Thus, using 17 together with 16, 10
14 we have n µ = nµ ˆβ, ˆγ [ D θ D θ w m ˆδ C m ] ˆγ ] δ w m ˆδ [ A m Π mb m I q Π mπ m w m ˆδ µ Iq Π mπ m δ op 1 = nµ ˆβ, ˆγ [D θ D θ w m ˆδ C m ] ˆγ w m ˆδ 0 I Π mb m Π mπ m w m ˆδ µ = nµ ˆβ, ˆγ [D θ w m ˆδ µ w m ˆδ µ = nµ ˆβ, ˆγ [D θ δ Iq Π mπ m δ op 1 w m ˆδ C m ] ˆγ Iq Π mπ m δ [ D θ Iq Π mπ m δ op 1 by 10 w m ˆδ C m ] ˆγ o p 1. w m ˆδ C m ]δ Hence, µ = ˆµ b ˆδo p n 1/2 and the intervals are asymptotically equivalent. Proof of Theorem 3. Also for this proof, it suffices to show that the intervals have the same centers asymptotically as the lengths are equal. Applying equation 9 in the appendix leads to ˆθ m = 1 n ˆQ 1 ˆQ 1 ˆQ xz Π ˆK m m Π m ˆQ zx ˆQ 1 X y ˆQ 1 ˆQ xz Π ˆK m m Π m Z y ˆK m Π m ˆQ zx ˆQ 1 X y ˆK m Π m Z y where the first block corresponds to ˆβ m and the second block corresponds to ˆγ m. Note that ˆβ ˆθ Ĉ m ˆγ =  m ˆγ Π ˆB, m m ˆγ, where  m = ˆQ 1 ˆQ xz I Π m ˆK m Π m ˆK 1 and ˆB m = ˆK m Π m ˆK 1. Therefore, the 11
15 difference of the centers satisfies [ 1 c w m ˆδ ] [ 1 ˆθ m ˆθ Ĉ m ˆγ = c w m ˆδ ˆβ m ˆβ ] Â m ˆγ ˆγ m Π ˆB. m m ˆγ 18 First, for the upper block ˆβ m ˆβ Â m ˆγ = ˆQ 1 ˆQ 1 ˆQ 1 ˆQ 1 ˆQ 1 = 0 p 1. ˆQ xz Π ˆK m m Π m ˆQ zx ˆQ 1 X y ˆQ 1 ˆQ xz Π ˆK m m Π m Z y ˆQ xz ˆK ˆQ zx ˆQ 1 X y ˆQ 1 ˆQ xz ˆKZ y ˆQ xz I Π m ˆK m Π m ˆK 1 ˆK ˆQ zx ˆQ 1 X y ˆKZ y Second, for the lower block ˆγ m Π ˆB m m ˆγ = Π m ˆγm ˆB m ˆγ = Π [ m ˆK m Π m ˆQ zx ˆQ 1 X y ˆK m Π m Z y ˆB m ˆK ˆQ zx ˆQ 1 X y ˆKZ y ] = Π m ˆB m ˆK ˆK m Π m ˆQ zx ˆQ 1 X Z y = 0 q 1 where the last equality holds because of ˆB m ˆK = ˆK m Π m ˆK 1 ˆK = ˆK m Π m. Thus, the difference between the centers in 18 may be further seen to be [ 1 c w m ˆδ ] [ 1 ˆθ m ˆθ Ĉ m ˆγ = c w m ˆδ 0 p 1 0 q 1 ] = 0 pq 1. Consequently, the confidence intervals for a linear function µθ = c θ of the parameters based on either frequentist model averaging or on least squares in the full model are equivalent, even in finite samples. References Akaike H 1974 A New Look at the Statistical odel Identification. IEEE Automat Contr 196: Ando T, Li KC 2014 A odel-averaging Approach for High-Dimensional Regression. J Am Stat Assoc : Berk R, Brown L, Buja A, Zhang K, Zhao L 2013 Valid post-selection inference. Ann Stat 412: Cheng TCF, Ing CK, Yu SH 2015 Toward optimal model averaging in regression models with time series errors. J Econometrics 1892:
16 Hansen BE 2007 Least squares model averaging. Econometrica 754: Hansen BE, Racine JS 2012 Jackknife model averaging. J Econometrics 1671:38 46 Harville DA 1997 atrix algebra from a statistician s perspective. Springer, New York Hjort NL, Claeskens G 2003 Frequentist odel Average Estimators. J Am Stat Assoc 98464: Kabaila P 1995 The Effect of odel Selection on Confidence Regions and Prediction Regions. Economet Theor 113: Kabaila P, Leeb H 2006 On the Large-Sample inimal Coverage Probability of Confidence Intervals After odel Selection. J Am Stat Assoc : Leeb H, Pötscher B 2005 odel Selection and Inference: Facts and Fiction. Economet Theor 211:21 59 Liu CA 2015 Distribution theory of the least squares averaging estimator. J Econometrics 1861: Liu Q, Okui R 2013 Heteroscedasticity-robust C p model averaging. Economet J 163: Pötscher B 1991 Effects of odel Selection on Inference. Economet Theor 72: Schwarz G 1978 Estimating the dimension of a model. Ann Stat 62: Wan ATK, Zhang X, Zou G 2010 Least squares model averaging by allows criterion. J Econometrics 1562: Wang H, Zhou SZF 2013 Interval Estimation by Frequentist odel Averaging. Commun Stat Theory 4223:
ESSAYS ON MODEL AVERAGING. Chu-An Liu. A dissertation submitted in partial fulfillment of the requirements for the degree of. Doctor of Philosophy
ESSAYS ON MODEL AVERAGING by Chu-An Liu A dissertation submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy (Economics) at the UNIVERSITY OF WISCONSIN MADISON 0 Date
More informationModel Averaging in Predictive Regressions
Model Averaging in Predictive Regressions Chu-An Liu and Biing-Shen Kuo Academia Sinica and National Chengchi University Mar 7, 206 Liu & Kuo (IEAS & NCCU) Model Averaging in Predictive Regressions Mar
More informationModel Selection, Estimation, and Bootstrap Smoothing. Bradley Efron Stanford University
Model Selection, Estimation, and Bootstrap Smoothing Bradley Efron Stanford University Estimation After Model Selection Usually: (a) look at data (b) choose model (linear, quad, cubic...?) (c) fit estimates
More informationUsing Invalid Instruments on Purpose: Focused Moment Selection and Averaging for GMM
Using Invalid Instruments on Purpose: Focused Moment Selection and Averaging for GMM Francis J. DiTraglia a a Faculty of Economics, University of Cambridge Abstract In finite samples, the use of an invalid
More informationConstruction of PoSI Statistics 1
Construction of PoSI Statistics 1 Andreas Buja and Arun Kumar Kuchibhotla Department of Statistics University of Pennsylvania September 8, 2018 WHOA-PSI 2018 1 Joint work with "Larry s Group" at Wharton,
More informationLeast Squares Model Averaging. Bruce E. Hansen University of Wisconsin. January 2006 Revised: August 2006
Least Squares Model Averaging Bruce E. Hansen University of Wisconsin January 2006 Revised: August 2006 Introduction This paper developes a model averaging estimator for linear regression. Model averaging
More informationMoment and IV Selection Approaches: A Comparative Simulation Study
Moment and IV Selection Approaches: A Comparative Simulation Study Mehmet Caner Esfandiar Maasoumi Juan Andrés Riquelme August 7, 2014 Abstract We compare three moment selection approaches, followed by
More informationA Measure of Robustness to Misspecification
A Measure of Robustness to Misspecification Susan Athey Guido W. Imbens December 2014 Graduate School of Business, Stanford University, and NBER. Electronic correspondence: athey@stanford.edu. Graduate
More information1 Motivation for Instrumental Variable (IV) Regression
ECON 370: IV & 2SLS 1 Instrumental Variables Estimation and Two Stage Least Squares Econometric Methods, ECON 370 Let s get back to the thiking in terms of cross sectional (or pooled cross sectional) data
More informationEcon 5150: Applied Econometrics Dynamic Demand Model Model Selection. Sung Y. Park CUHK
Econ 5150: Applied Econometrics Dynamic Demand Model Model Selection Sung Y. Park CUHK Simple dynamic models A typical simple model: y t = α 0 + α 1 y t 1 + α 2 y t 2 + x tβ 0 x t 1β 1 + u t, where y t
More informationSpecification Test for Instrumental Variables Regression with Many Instruments
Specification Test for Instrumental Variables Regression with Many Instruments Yoonseok Lee and Ryo Okui April 009 Preliminary; comments are welcome Abstract This paper considers specification testing
More informationEconometrics I KS. Module 2: Multivariate Linear Regression. Alexander Ahammer. This version: April 16, 2018
Econometrics I KS Module 2: Multivariate Linear Regression Alexander Ahammer Department of Economics Johannes Kepler University of Linz This version: April 16, 2018 Alexander Ahammer (JKU) Module 2: Multivariate
More informationModel Averaging in Predictive Regressions
MPRA Munich Personal RePEc Archive Model Averaging in Predictive Regressions Chu-An Liu and Biing-Shen Kuo Academia Sinica, National Chengchi University 8 March 206 Online at https://mpra.ub.uni-muenchen.de/706/
More informationFocused Information Criteria for Time Series
Focused Information Criteria for Time Series Gudmund Horn Hermansen with Nils Lid Hjort University of Oslo May 10, 2015 1/22 Do we really need more model selection criteria? There is already a wide range
More informationPost-Selection Inference
Classical Inference start end start Post-Selection Inference selected end model data inference data selection model data inference Post-Selection Inference Todd Kuffner Washington University in St. Louis
More informationMISCELLANEOUS TOPICS RELATED TO LIKELIHOOD. Copyright c 2012 (Iowa State University) Statistics / 30
MISCELLANEOUS TOPICS RELATED TO LIKELIHOOD Copyright c 2012 (Iowa State University) Statistics 511 1 / 30 INFORMATION CRITERIA Akaike s Information criterion is given by AIC = 2l(ˆθ) + 2k, where l(ˆθ)
More informationIllustration of the Varying Coefficient Model for Analyses the Tree Growth from the Age and Space Perspectives
TR-No. 14-06, Hiroshima Statistical Research Group, 1 11 Illustration of the Varying Coefficient Model for Analyses the Tree Growth from the Age and Space Perspectives Mariko Yamamura 1, Keisuke Fukui
More informationOn Post-selection Confidence Intervals in Linear Regression
Washington University in St. Louis Washington University Open Scholarship Arts & Sciences Electronic Theses and Dissertations Arts & Sciences Spring 5-2017 On Post-selection Confidence Intervals in Linear
More informationChoice is Suffering: A Focused Information Criterion for Model Selection
Choice is Suffering: A Focused Information Criterion for Model Selection Peter Behl, Holger Dette, Ruhr University Bochum, Manuel Frondel, Ruhr University Bochum and RWI, Harald Tauchmann, RWI Abstract.
More informationReview of Classical Least Squares. James L. Powell Department of Economics University of California, Berkeley
Review of Classical Least Squares James L. Powell Department of Economics University of California, Berkeley The Classical Linear Model The object of least squares regression methods is to model and estimate
More informationFall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.
1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n
More informationIntroductory Econometrics
Based on the textbook by Wooldridge: : A Modern Approach Robert M. Kunst robert.kunst@univie.ac.at University of Vienna and Institute for Advanced Studies Vienna November 23, 2013 Outline Introduction
More informationEcon 583 Final Exam Fall 2008
Econ 583 Final Exam Fall 2008 Eric Zivot December 11, 2008 Exam is due at 9:00 am in my office on Friday, December 12. 1 Maximum Likelihood Estimation and Asymptotic Theory Let X 1,...,X n be iid random
More informationLawrence D. Brown* and Daniel McCarthy*
Comments on the paper, An adaptive resampling test for detecting the presence of significant predictors by I. W. McKeague and M. Qian Lawrence D. Brown* and Daniel McCarthy* ABSTRACT: This commentary deals
More informationσ(a) = a N (x; 0, 1 2 ) dx. σ(a) = Φ(a) =
Until now we have always worked with likelihoods and prior distributions that were conjugate to each other, allowing the computation of the posterior distribution to be done in closed form. Unfortunately,
More informationFinal Exam. Economics 835: Econometrics. Fall 2010
Final Exam Economics 835: Econometrics Fall 2010 Please answer the question I ask - no more and no less - and remember that the correct answer is often short and simple. 1 Some short questions a) For each
More informationModel Selection Tutorial 2: Problems With Using AIC to Select a Subset of Exposures in a Regression Model
Model Selection Tutorial 2: Problems With Using AIC to Select a Subset of Exposures in a Regression Model Centre for Molecular, Environmental, Genetic & Analytic (MEGA) Epidemiology School of Population
More informationHigh-Dimensional AICs for Selection of Redundancy Models in Discriminant Analysis. Tetsuro Sakurai, Takeshi Nakada and Yasunori Fujikoshi
High-Dimensional AICs for Selection of Redundancy Models in Discriminant Analysis Tetsuro Sakurai, Takeshi Nakada and Yasunori Fujikoshi Faculty of Science and Engineering, Chuo University, Kasuga, Bunkyo-ku,
More informationAsymptotic Multivariate Kriging Using Estimated Parameters with Bayesian Prediction Methods for Non-linear Predictands
Asymptotic Multivariate Kriging Using Estimated Parameters with Bayesian Prediction Methods for Non-linear Predictands Elizabeth C. Mannshardt-Shamseldin Advisor: Richard L. Smith Duke University Department
More informationF & B Approaches to a simple model
A6523 Signal Modeling, Statistical Inference and Data Mining in Astrophysics Spring 215 http://www.astro.cornell.edu/~cordes/a6523 Lecture 11 Applications: Model comparison Challenges in large-scale surveys
More informationTesting Restrictions and Comparing Models
Econ. 513, Time Series Econometrics Fall 00 Chris Sims Testing Restrictions and Comparing Models 1. THE PROBLEM We consider here the problem of comparing two parametric models for the data X, defined by
More informationLinear Instrumental Variables Model Averaging Estimation
Linear Instrumental Variables Model Averaging Estimation Luis F. Martins Department of Quantitative Methods, ISCE-LUI, Portugal Centre for International Macroeconomic Studies CIMS, UK luis.martins@iscte.pt
More informationOn the Behavior of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models
On the Behavior of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models Thomas Kneib Department of Mathematics Carl von Ossietzky University Oldenburg Sonja Greven Department of
More informationGeneralized Linear Models
Generalized Linear Models Lecture 3. Hypothesis testing. Goodness of Fit. Model diagnostics GLM (Spring, 2018) Lecture 3 1 / 34 Models Let M(X r ) be a model with design matrix X r (with r columns) r n
More informationGeneralized Cp (GCp) in a Model Lean Framework
Generalized Cp (GCp) in a Model Lean Framework Linda Zhao University of Pennsylvania Dedicated to Lawrence Brown (1940-2018) September 9th, 2018 WHOA 3 Joint work with Larry Brown, Juhui Cai, Arun Kumar
More informationConsistency of test based method for selection of variables in high dimensional two group discriminant analysis
https://doi.org/10.1007/s42081-019-00032-4 ORIGINAL PAPER Consistency of test based method for selection of variables in high dimensional two group discriminant analysis Yasunori Fujikoshi 1 Tetsuro Sakurai
More informationBirkbeck Working Papers in Economics & Finance
ISSN 1745-8587 Birkbeck Working Papers in Economics & Finance Department of Economics, Mathematics and Statistics BWPEF 1809 A Note on Specification Testing in Some Structural Regression Models Walter
More informationData Mining Stat 588
Data Mining Stat 588 Lecture 02: Linear Methods for Regression Department of Statistics & Biostatistics Rutgers University September 13 2011 Regression Problem Quantitative generic output variable Y. Generic
More informationRegression I: Mean Squared Error and Measuring Quality of Fit
Regression I: Mean Squared Error and Measuring Quality of Fit -Applied Multivariate Analysis- Lecturer: Darren Homrighausen, PhD 1 The Setup Suppose there is a scientific problem we are interested in solving
More informationStatistica Sinica Preprint No: SS R2
Statistica Sinica Preprint No: SS-2017-0034.R2 Title OPTIMAL MODEL AVERAGING OF VARYING COEFFICIENT MODELS Manuscript ID SS-2017-0034.R2 URL http://www.stat.sinica.edu.tw/statistica/ DOI 10.5705/ss.202017.0034
More informationSelection Criteria Based on Monte Carlo Simulation and Cross Validation in Mixed Models
Selection Criteria Based on Monte Carlo Simulation and Cross Validation in Mixed Models Junfeng Shang Bowling Green State University, USA Abstract In the mixed modeling framework, Monte Carlo simulation
More information1 Introduction to Generalized Least Squares
ECONOMICS 7344, Spring 2017 Bent E. Sørensen April 12, 2017 1 Introduction to Generalized Least Squares Consider the model Y = Xβ + ɛ, where the N K matrix of regressors X is fixed, independent of the
More informationLECTURE ON HAC COVARIANCE MATRIX ESTIMATION AND THE KVB APPROACH
LECURE ON HAC COVARIANCE MARIX ESIMAION AND HE KVB APPROACH CHUNG-MING KUAN Institute of Economics Academia Sinica October 20, 2006 ckuan@econ.sinica.edu.tw www.sinica.edu.tw/ ckuan Outline C.-M. Kuan,
More informationA New Combined Approach for Inference in High-Dimensional Regression Models with Correlated Variables
A New Combined Approach for Inference in High-Dimensional Regression Models with Correlated Variables Niharika Gauraha and Swapan Parui Indian Statistical Institute Abstract. We consider the problem of
More informationAnalysis of Cross-Sectional Data
Analysis of Cross-Sectional Data Kevin Sheppard http://www.kevinsheppard.com Oxford MFE This version: November 8, 2017 November 13 14, 2017 Outline Econometric models Specification that can be analyzed
More informationLinear IV and Simultaneous Equations
Linear IV and Daniel Schmierer Econ 312 April 6, 2007 Setup Linear regression model Y = X β + ε (1) Endogeneity of X means that X and ε are correlated, ie. E(X ε) 0. Suppose we observe another variable
More informationSome Theories about Backfitting Algorithm for Varying Coefficient Partially Linear Model
Some Theories about Backfitting Algorithm for Varying Coefficient Partially Linear Model 1. Introduction Varying-coefficient partially linear model (Zhang, Lee, and Song, 2002; Xia, Zhang, and Tong, 2004;
More informationOn the Behavior of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models
On the Behavior of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models Thomas Kneib Institute of Statistics and Econometrics Georg-August-University Göttingen Department of Statistics
More informationSingle Equation Linear GMM with Serially Correlated Moment Conditions
Single Equation Linear GMM with Serially Correlated Moment Conditions Eric Zivot October 28, 2009 Univariate Time Series Let {y t } be an ergodic-stationary time series with E[y t ]=μ and var(y t )
More informationGeneralized Method of Moment
Generalized Method of Moment CHUNG-MING KUAN Department of Finance & CRETA National Taiwan University June 16, 2010 C.-M. Kuan (Finance & CRETA, NTU Generalized Method of Moment June 16, 2010 1 / 32 Lecture
More informationSpecification errors in linear regression models
Specification errors in linear regression models Jean-Marie Dufour McGill University First version: February 2002 Revised: December 2011 This version: December 2011 Compiled: December 9, 2011, 22:34 This
More informationInference For High Dimensional M-estimates. Fixed Design Results
: Fixed Design Results Lihua Lei Advisors: Peter J. Bickel, Michael I. Jordan joint work with Peter J. Bickel and Noureddine El Karoui Dec. 8, 2016 1/57 Table of Contents 1 Background 2 Main Results and
More informationPoSI Valid Post-Selection Inference
PoSI Valid Post-Selection Inference Andreas Buja joint work with Richard Berk, Lawrence Brown, Kai Zhang, Linda Zhao Department of Statistics, The Wharton School University of Pennsylvania Philadelphia,
More informationConfidence Intervals in Ridge Regression using Jackknife and Bootstrap Methods
Chapter 4 Confidence Intervals in Ridge Regression using Jackknife and Bootstrap Methods 4.1 Introduction It is now explicable that ridge regression estimator (here we take ordinary ridge estimator (ORE)
More informationEconomic modelling and forecasting
Economic modelling and forecasting 2-6 February 2015 Bank of England he generalised method of moments Ole Rummel Adviser, CCBS at the Bank of England ole.rummel@bankofengland.co.uk Outline Classical estimation
More informationEfficient Estimation of Population Quantiles in General Semiparametric Regression Models
Efficient Estimation of Population Quantiles in General Semiparametric Regression Models Arnab Maity 1 Department of Statistics, Texas A&M University, College Station TX 77843-3143, U.S.A. amaity@stat.tamu.edu
More informationSMOOTHED BLOCK EMPIRICAL LIKELIHOOD FOR QUANTILES OF WEAKLY DEPENDENT PROCESSES
Statistica Sinica 19 (2009), 71-81 SMOOTHED BLOCK EMPIRICAL LIKELIHOOD FOR QUANTILES OF WEAKLY DEPENDENT PROCESSES Song Xi Chen 1,2 and Chiu Min Wong 3 1 Iowa State University, 2 Peking University and
More informationBootstrap. Director of Center for Astrostatistics. G. Jogesh Babu. Penn State University babu.
Bootstrap G. Jogesh Babu Penn State University http://www.stat.psu.edu/ babu Director of Center for Astrostatistics http://astrostatistics.psu.edu Outline 1 Motivation 2 Simple statistical problem 3 Resampling
More informationBayesian methods in economics and finance
1/26 Bayesian methods in economics and finance Linear regression: Bayesian model selection and sparsity priors Linear Regression 2/26 Linear regression Model for relationship between (several) independent
More informationHeteroskedasticity. Part VII. Heteroskedasticity
Part VII Heteroskedasticity As of Oct 15, 2015 1 Heteroskedasticity Consequences Heteroskedasticity-robust inference Testing for Heteroskedasticity Weighted Least Squares (WLS) Feasible generalized Least
More informationThe Bootstrap: Theory and Applications. Biing-Shen Kuo National Chengchi University
The Bootstrap: Theory and Applications Biing-Shen Kuo National Chengchi University Motivation: Poor Asymptotic Approximation Most of statistical inference relies on asymptotic theory. Motivation: Poor
More informationModel comparison and selection
BS2 Statistical Inference, Lectures 9 and 10, Hilary Term 2008 March 2, 2008 Hypothesis testing Consider two alternative models M 1 = {f (x; θ), θ Θ 1 } and M 2 = {f (x; θ), θ Θ 2 } for a sample (X = x)
More informationSummary and discussion of: Exact Post-selection Inference for Forward Stepwise and Least Angle Regression Statistics Journal Club
Summary and discussion of: Exact Post-selection Inference for Forward Stepwise and Least Angle Regression Statistics Journal Club 36-825 1 Introduction Jisu Kim and Veeranjaneyulu Sadhanala In this report
More informationGoodness-of-Fit Tests for Time Series Models: A Score-Marked Empirical Process Approach
Goodness-of-Fit Tests for Time Series Models: A Score-Marked Empirical Process Approach By Shiqing Ling Department of Mathematics Hong Kong University of Science and Technology Let {y t : t = 0, ±1, ±2,
More informationA better way to bootstrap pairs
A better way to bootstrap pairs Emmanuel Flachaire GREQAM - Université de la Méditerranée CORE - Université Catholique de Louvain April 999 Abstract In this paper we are interested in heteroskedastic regression
More informationBayesian Nonparametric Point Estimation Under a Conjugate Prior
University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 5-15-2002 Bayesian Nonparametric Point Estimation Under a Conjugate Prior Xuefeng Li University of Pennsylvania Linda
More informationORTHOGONALITY TESTS IN LINEAR MODELS SEUNG CHAN AHN ARIZONA STATE UNIVERSITY ABSTRACT
ORTHOGONALITY TESTS IN LINEAR MODELS SEUNG CHAN AHN ARIZONA STATE UNIVERSITY ABSTRACT This paper considers several tests of orthogonality conditions in linear models where stochastic errors may be heteroskedastic
More informationThe Behaviour of the Akaike Information Criterion when Applied to Non-nested Sequences of Models
The Behaviour of the Akaike Information Criterion when Applied to Non-nested Sequences of Models Centre for Molecular, Environmental, Genetic & Analytic (MEGA) Epidemiology School of Population Health
More informationSparse Linear Models (10/7/13)
STA56: Probabilistic machine learning Sparse Linear Models (0/7/) Lecturer: Barbara Engelhardt Scribes: Jiaji Huang, Xin Jiang, Albert Oh Sparsity Sparsity has been a hot topic in statistics and machine
More informationLTI Systems, Additive Noise, and Order Estimation
LTI Systems, Additive oise, and Order Estimation Soosan Beheshti, Munther A. Dahleh Laboratory for Information and Decision Systems Department of Electrical Engineering and Computer Science Massachusetts
More informationWorking Paper No Maximum score type estimators
Warsaw School of Economics Institute of Econometrics Department of Applied Econometrics Department of Applied Econometrics Working Papers Warsaw School of Economics Al. iepodleglosci 64 02-554 Warszawa,
More informationApproximate Distributions of the Likelihood Ratio Statistic in a Structural Equation with Many Instruments
CIRJE-F-466 Approximate Distributions of the Likelihood Ratio Statistic in a Structural Equation with Many Instruments Yukitoshi Matsushita CIRJE, Faculty of Economics, University of Tokyo February 2007
More informationConsistency of Test-based Criterion for Selection of Variables in High-dimensional Two Group-Discriminant Analysis
Consistency of Test-based Criterion for Selection of Variables in High-dimensional Two Group-Discriminant Analysis Yasunori Fujikoshi and Tetsuro Sakurai Department of Mathematics, Graduate School of Science,
More informationAsymptotic inference for a nonstationary double ar(1) model
Asymptotic inference for a nonstationary double ar() model By SHIQING LING and DONG LI Department of Mathematics, Hong Kong University of Science and Technology, Hong Kong maling@ust.hk malidong@ust.hk
More informationMS&E 226: Small Data
MS&E 226: Small Data Lecture 12: Frequentist properties of estimators (v4) Ramesh Johari ramesh.johari@stanford.edu 1 / 39 Frequentist inference 2 / 39 Thinking like a frequentist Suppose that for some
More informationCross-Validation with Confidence
Cross-Validation with Confidence Jing Lei Department of Statistics, Carnegie Mellon University UMN Statistics Seminar, Mar 30, 2017 Overview Parameter est. Model selection Point est. MLE, M-est.,... Cross-validation
More informationAn Asymptotic Theory for Model Selection Inference in General Semiparametric Problems
An Asymptotic Theory for Model Selection Inference in General Semiparametric Problems By Gerda Claeskens ORSTAT and University Center for Statistics, K.U. Leuven, Naamsestraat 69, B-3000 Leuven, Belgium.
More informationA strong consistency proof for heteroscedasticity and autocorrelation consistent covariance matrix estimators
A strong consistency proof for heteroscedasticity and autocorrelation consistent covariance matrix estimators Robert M. de Jong Department of Economics Michigan State University 215 Marshall Hall East
More informationBayesian Estimation of Regression Coefficients Under Extended Balanced Loss Function
Communications in Statistics Theory and Methods, 43: 4253 4264, 2014 Copyright Taylor & Francis Group, LLC ISSN: 0361-0926 print / 1532-415X online DOI: 10.1080/03610926.2012.725498 Bayesian Estimation
More informationBayesian Indirect Inference and the ABC of GMM
Bayesian Indirect Inference and the ABC of GMM Michael Creel, Jiti Gao, Han Hong, Dennis Kristensen Universitat Autónoma, Barcelona Graduate School of Economics, and MOVE Monash University Stanford University
More informationSUPPLEMENT TO PARAMETRIC OR NONPARAMETRIC? A PARAMETRICNESS INDEX FOR MODEL SELECTION. University of Minnesota
Submitted to the Annals of Statistics arxiv: math.pr/0000000 SUPPLEMENT TO PARAMETRIC OR NONPARAMETRIC? A PARAMETRICNESS INDEX FOR MODEL SELECTION By Wei Liu and Yuhong Yang University of Minnesota In
More informationESTIMATING THE MEAN LEVEL OF FINE PARTICULATE MATTER: AN APPLICATION OF SPATIAL STATISTICS
ESTIMATING THE MEAN LEVEL OF FINE PARTICULATE MATTER: AN APPLICATION OF SPATIAL STATISTICS Richard L. Smith Department of Statistics and Operations Research University of North Carolina Chapel Hill, N.C.,
More informationLocation Properties of Point Estimators in Linear Instrumental Variables and Related Models
Location Properties of Point Estimators in Linear Instrumental Variables and Related Models Keisuke Hirano Department of Economics University of Arizona hirano@u.arizona.edu Jack R. Porter Department of
More informationLasso Maximum Likelihood Estimation of Parametric Models with Singular Information Matrices
Article Lasso Maximum Likelihood Estimation of Parametric Models with Singular Information Matrices Fei Jin 1,2 and Lung-fei Lee 3, * 1 School of Economics, Shanghai University of Finance and Economics,
More informationLecture: Simultaneous Equation Model (Wooldridge s Book Chapter 16)
Lecture: Simultaneous Equation Model (Wooldridge s Book Chapter 16) 1 2 Model Consider a system of two regressions y 1 = β 1 y 2 + u 1 (1) y 2 = β 2 y 1 + u 2 (2) This is a simultaneous equation model
More informationABSTRACT. Effects of Model Selection on the Coverage Probability of Confidence Intervals in Binary-Response Logistic Regression
ABSTRACT Title of Dissertation: Effects of Model Selection on the Coverage Probability of Confidence Intervals in Binary-Response Logistic Regression Dongquan Zhang, Doctor of Philosophy, 2008 Dissertation
More informationExtended Bayesian Information Criteria for Model Selection with Large Model Spaces
Extended Bayesian Information Criteria for Model Selection with Large Model Spaces Jiahua Chen, University of British Columbia Zehua Chen, National University of Singapore (Biometrika, 2008) 1 / 18 Variable
More informationNonconcave Penalized Likelihood with A Diverging Number of Parameters
Nonconcave Penalized Likelihood with A Diverging Number of Parameters Jianqing Fan and Heng Peng Presenter: Jiale Xu March 12, 2010 Jianqing Fan and Heng Peng Presenter: JialeNonconcave Xu () Penalized
More informationSize Distortion and Modi cation of Classical Vuong Tests
Size Distortion and Modi cation of Classical Vuong Tests Xiaoxia Shi University of Wisconsin at Madison March 2011 X. Shi (UW-Mdsn) H 0 : LR = 0 IUPUI 1 / 30 Vuong Test (Vuong, 1989) Data fx i g n i=1.
More informationUncertain Inference and Artificial Intelligence
March 3, 2011 1 Prepared for a Purdue Machine Learning Seminar Acknowledgement Prof. A. P. Dempster for intensive collaborations on the Dempster-Shafer theory. Jianchun Zhang, Ryan Martin, Duncan Ermini
More informationEconometrics II - EXAM Answer each question in separate sheets in three hours
Econometrics II - EXAM Answer each question in separate sheets in three hours. Let u and u be jointly Gaussian and independent of z in all the equations. a Investigate the identification of the following
More informationSome Approximations of the Logistic Distribution with Application to the Covariance Matrix of Logistic Regression
Working Paper 2013:9 Department of Statistics Some Approximations of the Logistic Distribution with Application to the Covariance Matrix of Logistic Regression Ronnie Pingel Working Paper 2013:9 June
More informationNonlinear minimization estimators in the presence of cointegrating relations
Nonlinear minimization estimators in the presence of cointegrating relations Robert M. de Jong January 31, 2000 Abstract In this paper, we consider estimation of a long-run and a short-run parameter jointly
More informationChapter 4: Constrained estimators and tests in the multiple linear regression model (Part III)
Chapter 4: Constrained estimators and tests in the multiple linear regression model (Part III) Florian Pelgrin HEC September-December 2010 Florian Pelgrin (HEC) Constrained estimators September-December
More informationSelective Inference for Effect Modification
Inference for Modification (Joint work with Dylan Small and Ashkan Ertefaie) Department of Statistics, University of Pennsylvania May 24, ACIC 2017 Manuscript and slides are available at http://www-stat.wharton.upenn.edu/~qyzhao/.
More informationLong-Run Covariability
Long-Run Covariability Ulrich K. Müller and Mark W. Watson Princeton University October 2016 Motivation Study the long-run covariability/relationship between economic variables great ratios, long-run Phillips
More informationEconomics Division University of Southampton Southampton SO17 1BJ, UK. Title Overlapping Sub-sampling and invariance to initial conditions
Economics Division University of Southampton Southampton SO17 1BJ, UK Discussion Papers in Economics and Econometrics Title Overlapping Sub-sampling and invariance to initial conditions By Maria Kyriacou
More informationTime Invariant Variables and Panel Data Models : A Generalised Frisch- Waugh Theorem and its Implications
Time Invariant Variables and Panel Data Models : A Generalised Frisch- Waugh Theorem and its Implications Jaya Krishnakumar No 2004.01 Cahiers du département d économétrie Faculté des sciences économiques
More informationModification and Improvement of Empirical Likelihood for Missing Response Problem
UW Biostatistics Working Paper Series 12-30-2010 Modification and Improvement of Empirical Likelihood for Missing Response Problem Kwun Chuen Gary Chan University of Washington - Seattle Campus, kcgchan@u.washington.edu
More informationQuick Review on Linear Multiple Regression
Quick Review on Linear Multiple Regression Mei-Yuan Chen Department of Finance National Chung Hsing University March 6, 2007 Introduction for Conditional Mean Modeling Suppose random variables Y, X 1,
More information